© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12908
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flu
    -0.08
     välja
    -0.08
     embodied
    -0.07
    HB
    -0.07
     aanbieden
    -0.07
     த
    -0.07
    iji
    -0.07
    -hit
    -0.07
     hozz
    -0.07
     toeg
    -0.07
    POSITIVE LOGITS
    юй
    0.08
     AWESOME
    0.08
     uc
    0.08
     अत
    0.08
    崎
    0.08
    图库
    0.08
     COMPONENT
    0.08
    вав
    0.08
    vid
    0.08
     GREAT
    0.08
    Activations Density 0.023%

    No Known Activations